public static void DoAutoML()
{
// Load Data
IDataView trainingDataView = mlContext.Data.LoadFromTextFile <ModelInput>(
path: TRAIN_DATA_FILEPATH,
hasHeader: true,
separatorChar: ',',
allowQuoting: true,
allowSparse: false);
var experimentSettings = new MulticlassExperimentSettings();
experimentSettings.MaxExperimentTimeInSeconds = 10;
MulticlassClassificationExperiment experiment = mlContext.Auto().CreateMulticlassClassificationExperiment(experimentSettings);
var dataProcessPipeline = mlContext.Transforms.Categorical.OneHotEncoding(new[] { new InputOutputColumnPair("Vehicle Type", "Vehicle Type"), new InputOutputColumnPair("Day", "Day") })
.Append(mlContext.Transforms.Concatenate("Features", new[] { "Vehicle Type", "Day", "Ride Distance (km)", "Hour" }));
ExperimentResult <Microsoft.ML.Data.MulticlassClassificationMetrics> experimentResult = experiment.Execute(trainingDataView, labelColumnName: "Saving", preFeaturizer: dataProcessPipeline);
var metrics = experimentResult.BestRun.ValidationMetrics;
Console.WriteLine($"Macro Accuracy: {metrics.MacroAccuracy:0.##}");
Console.WriteLine($"Micro Accuracy: {metrics.MicroAccuracy:0.##}");
// Save model
SaveModel(mlContext, experimentResult.BestRun.Model, MODEL_FILEPATH, trainingDataView.Schema);
}
public static void CreateExperiment()
{
// Load Data
var tmpPath = GetAbsolutePath(TRAIN_DATA_FILEPATH);
IDataView trainingDataView = mlContext.Data.LoadFromTextFile <ModelInput>(
path: tmpPath,
hasHeader: true,
separatorChar: '\t',
allowQuoting: true,
allowSparse: false);
IDataView testDataView = mlContext.Data.BootstrapSample(trainingDataView);
// STEP 2: Run AutoML experiment
Console.WriteLine($"Running AutoML Multiclass classification experiment for {ExperimentTime} seconds...");
//ExperimentResult<MulticlassClassificationMetrics> experimentResult = mlContext.Auto()
// .CreateMulticlassClassificationExperiment(ExperimentTime)
// .Execute(trainingDataView, labelColumnName: "reservation_status");
MulticlassClassificationExperiment experiment = mlContext.Auto()
.CreateMulticlassClassificationExperiment(ExperimentTime);
ExperimentResult <MulticlassClassificationMetrics> experimentResult = experiment.Execute(trainingDataView, labelColumnName: "reservation_status");
// STEP 3: Print metric from the best model
RunDetail <MulticlassClassificationMetrics> bestRun = experimentResult.BestRun;
Console.WriteLine($"Total models produced: {experimentResult.RunDetails.Count()}");
Console.WriteLine($"Best model's trainer: {bestRun.TrainerName}");
Console.WriteLine($"Metrics of best model from validation data --");
PrintMulticlassClassificationMetrics(bestRun.ValidationMetrics);
// STEP 4: Evaluate test data
IDataView testDataViewWithBestScore = bestRun.Model.Transform(testDataView);
try
{
var testMetrics = mlContext.MulticlassClassification.CrossValidate(testDataViewWithBestScore, bestRun.Estimator, numberOfFolds: 5, labelColumnName: "reservation_status");
Console.WriteLine($"Metrics of best model on test data --");
PrintMulticlassClassificationFoldsAverageMetrics(testMetrics);
}
catch
{
Console.WriteLine($"Metrics not supported in this version");
}
// Save model
tmpPath = GetAbsolutePath(MODEL_FILEPATH2);
SaveModel(mlContext, bestRun.Model, tmpPath, trainingDataView.Schema);
}
public void SetUpExperiment()
{
var settings = new MulticlassExperimentSettings
{
MaxExperimentTimeInSeconds = 180,
OptimizingMetric = MulticlassClassificationMetric.LogLoss,
CacheDirectory = null
};
// These two trainers yield no metrics in UWP:
settings.Trainers.Remove(MulticlassClassificationTrainer.FastTreeOva);
settings.Trainers.Remove(MulticlassClassificationTrainer.FastForestOva);
_experiment = MLContext.Auto().CreateMulticlassClassificationExperiment(settings);
}
static void Main(string[] args)
{
MulticlassClassificationExperiment.Run();
}
